Expand AI logo
DocsDocs
Glow Active
API Reference
Login

Documentation

Get Started

OverviewWhy ExpandQuickstartWays to Use Expand

Agent Quickstarts

OverviewExpand SkillClaude CodeCursorCodexOpenCodeSkill-Based AgentsOther MCP Clients

Fetch

OverviewHow Fetch WorksOutput ModelInclude OptionsBrowser BehaviorHighlightsPlayground & ReplayBatched Fetch

Reference

API ReferenceCLI CommandsMCP Tools & ResourcesTypeScript SDKPython SDK

Account & Billing

Pricing & UsageTiersFAQ

Machine-Readable Docs

start.mdllms.txtllms-full.txtDocs as Markdown
Browse docs

Get Started

OverviewWhy ExpandQuickstartWays to Use Expand

Agent Quickstarts

OverviewExpand SkillClaude CodeCursorCodexOpenCodeSkill-Based AgentsOther MCP Clients

Fetch

OverviewHow Fetch WorksOutput ModelInclude OptionsBrowser BehaviorHighlightsPlayground & ReplayBatched Fetch

Reference

API ReferenceCLI CommandsMCP Tools & ResourcesTypeScript SDKPython SDK

Account & Billing

Pricing & UsageTiersFAQ

Machine-Readable Docs

start.mdllms.txtllms-full.txtDocs as Markdown

FAQ

Short answers to common questions about Fetch, agents, Highlights, billing, tiers, and reference docs.

Short answers to common questions about Fetch, agents, Highlights, billing, tiers, and reference docs. Each answer is two to five sentences and links to the canonical page when you need detail. Jump to a group:

Using Expand

Fetch, usage surfaces, and which path to pick.

Fetch output

Markdown, State JSON, progressive disclosure, Include Options.

Highlights and citations

Searching captures and building evidence links.

Agents

Hooks, the Expand Skill, MCP, and auth.

Billing and tiers

Credits, usage, browser concurrency, provisioned slots.

Reference and Markdown docs

API Reference, schemas, and machine-readable routes.

Using Expand

What is Fetch?

Fetch is Expand's core product: it renders a live page and returns agent-ready Markdown, State JSON, evidence, and replayable artifacts. Start with Fetch Overview.

Are CLI, MCP, SDKs, and the API separate products?

No. They are ways to use Fetch. Use the CLI for terminal workflows, SDKs or the API for app code, MCP for agent tools, and hooks or skills for agent harness integrations. See Ways to Use Expand.

Which path should I use?

NeedPath
Try one URL from your terminalQuickstart / CLI
Add Fetch to an appTypeScript SDK, Python SDK, or API Reference
Give a coding agent web contextAgent Quickstarts

When should I use the CLI instead of an SDK?

Use the CLI for local inspection, scripts, and agent shell workflows. Use an SDK or the API when Fetch is part of your application code. See CLI Commands and the TypeScript and Python SDKs.

Fetch output

Why does /v1/fetch return Markdown directly?

/v1/fetch is optimized for the common path: get the main readable document quickly. Use /v1/fetch/json when you need metadata, State JSON, snapshot IDs, or structured response fields. See Output Model.

When should I use JSON Mode?

Use JSON Mode when application code needs Main Markdown plus State JSON, metadata, links, Highlights, or snapshot references in one object response. See Output Model and the TypeScript and Python SDKs.

What are Main Markdown and State JSON?

Main Markdown is the primary readable page content. State JSON is structured page and network state that can answer questions Markdown alone may miss. See How Fetch Works.

Is State JSON always included?

State JSON is part of the core output model for JSON Mode, but large or secondary state can be referenced through progressive disclosure instead of being forced into the main response. See Output Model.

What is progressive disclosure?

Progressive disclosure means Fetch gives the agent the pragmatic default first, while preserving references to deeper context when the task needs it. See How Fetch Works.

Are Appendix links, snapshotId, or moreTokens missing data?

Usually no. They are handles to more context, replay, evidence, or continued output. Fetch avoids flooding the default response while keeping deeper material recoverable. See Output Model and Playground & Replay.

Should I turn on every Include Option?

No. Start with defaults. Add Include Options only when the task needs a specific artifact such as HTML, screenshot, links, response metadata, Appendix, or State JSON detail. See Include Options.

Does Batched Fetch support every single-Fetch output?

No. Batched Fetch is optimized for many URLs and has limitations. It does not support every single-Fetch artifact or Highlights path. See Batched Fetch.

Highlights and citations

What are Highlights?

Highlights finds the most relevant snippets inside a Fetch capture so an agent can ask focused questions without loading the whole document again. See Highlights.

Why do technical surfaces still say fetch_search, /v1/fetch/search, or expandai search?

Highlights is the product name. Some technical surfaces keep their existing endpoint, tool, or command names for compatibility. See Highlights and the API Reference.

Does Highlights re-fetch the page?

Snapshot Highlights searches an existing capture by snapshot ID. Inline Highlights can run as part of a Fetch request. See Highlights.

Can Highlights search Markdown, State JSON, and Appendix?

Yes, when those artifacts are present in the searchable corpus. Defaults and include choices determine what is available. See Highlights and Include Options.

Do Highlights results include citations?

Highlights results include enough location information to build evidence links. MCP can add citationUrl fields; raw API and SDK responses may require using citation helper functions. See Playground & Replay and the TypeScript and Python SDKs.

Can I show Playground citation links to my own users?

Yes, if the captured content is safe to share publicly. Playground links are designed for evidence inspection and can be embedded into deep research products, but you should not expose private pages, secrets, or customer data. See Playground & Replay.

Agents

What is the difference between hooks, the Expand Skill, and MCP?

Hooks can route a host's native web fetch behavior through Expand. The Skill teaches an agent how to use Expand. MCP gives an agent native Fetch tools. See Agent Quickstarts.

Which agents support hooks?

First-class hook support exists for Claude Code and OpenCode. Cursor and Codex use Skill plus MCP instead. See Claude Code and OpenCode.

Is installing the Expand Skill enough?

It can be enough when the agent can read the skill and run terminal commands. Add MCP when you want native tool calls or when the agent should not rely only on shell commands. See Expand Skill.

Should agent setup use expandai login or EXPAND_API_KEY?

For normal local agent setup, use expandai login; the local MCP server and CLI read local auth. Use EXPAND_API_KEY for SDK, API, server, or CI-style contexts. See Agent Quickstarts and the TypeScript and Python SDKs.

What is /start.md?

/start.md is the canonical public setup prompt for agents. Give it to an agent when you want it to choose the right Expand setup path. See start.md.

Why can't my agent see the installed skill or MCP server?

Most often, the install was run from the wrong directory, the agent needs to restart, or the MCP config was written to a different scope than the agent is using. See Agent Quickstarts and your agent's setup page.

Billing and tiers

Is Expand billed by tokens?

No. Expand helps agents answer more questions with fewer tokens, but billing is credit and usage based, not token based. See Pricing & Usage.

What creates billable usage?

Fetch usage is metered through billable outputs. Highlights and summaries add usage when requested. See Pricing & Usage.

What are credits?

Credits are a dollar balance on your organization. Usage draws down that balance as billable outputs are recorded. See Pricing & Usage.

What happens when my balance reaches zero?

Usage can be blocked until funds are available again. Auto-Recharge helps avoid hitting a zero-balance block. See Pricing & Usage.

Are tiers pricing plans?

No. Tiers are automatic browser-concurrency unlocks based on successful spend and time since your first transaction. See Tiers.

Why am I not in the next tier after spending enough?

Most tiers require both successful spend and elapsed time since the first transaction. If spend is high enough but the time requirement has not elapsed, the next tier is not active yet. See Tiers.

What is browser concurrency?

Browser concurrency is the number of browser-backed Fetch jobs that can run at the same time before additional work queues. See Tiers and Batched Fetch.

Do provisioned browser slots upgrade my tier?

No. Provisioned slots add browser capacity on top of your tier. They do not change your tier status. See Tiers.

When do provisioned slot upgrades and downgrades take effect?

Upgrades apply immediately. Downgrades take effect at the next billing cycle. See Tiers.

Reference and Markdown docs

Why is API Reference separate from authored docs?

Authored docs explain concepts and workflows. API Reference owns exact endpoint contracts, schemas, errors, and generated examples. Open the API Reference.

Where do exact request and response schemas live?

Use API Reference for exact endpoint schemas. Authored docs intentionally link to reference pages instead of duplicating full schemas. Open the API Reference.

Can agents read the docs as Markdown?

Yes. Docs and API Reference pages are available through Markdown-oriented routes, and machine-readable docs provide compact agent entry points. See Docs as Markdown.

What is the difference between /start.md, llms.txt, and llms-full.txt?

/start.md is an agent setup prompt. llms.txt is a compact docs index. llms-full.txt is a larger docs bundle for agents that need more context. See start.md, llms.txt, and llms-full.txt.

Can API Reference pages be fetched as Markdown?

Yes. The API Reference area stays available through Markdown routes and Accept: text/markdown requests. Open the API Reference.

PreviousTiers
Nextstart.md

On This Page

Using ExpandWhat is Fetch?Are CLI, MCP, SDKs, and the API separate products?Which path should I use?When should I use the CLI instead of an SDK?Fetch outputWhy does /v1/fetch return Markdown directly?When should I use JSON Mode?What are Main Markdown and State JSON?Is State JSON always included?What is progressive disclosure?Are Appendix links, snapshotId, or moreTokens missing data?Should I turn on every Include Option?Does Batched Fetch support every single-Fetch output?Highlights and citationsWhat are Highlights?Why do technical surfaces still say fetch_search, /v1/fetch/search, or expandai search?Does Highlights re-fetch the page?Can Highlights search Markdown, State JSON, and Appendix?Do Highlights results include citations?Can I show Playground citation links to my own users?AgentsWhat is the difference between hooks, the Expand Skill, and MCP?Which agents support hooks?Is installing the Expand Skill enough?Should agent setup use expandai login or EXPAND_API_KEY?What is /start.md?Why can't my agent see the installed skill or MCP server?Billing and tiersIs Expand billed by tokens?What creates billable usage?What are credits?What happens when my balance reaches zero?Are tiers pricing plans?Why am I not in the next tier after spending enough?What is browser concurrency?Do provisioned browser slots upgrade my tier?When do provisioned slot upgrades and downgrades take effect?Reference and Markdown docsWhy is API Reference separate from authored docs?Where do exact request and response schemas live?Can agents read the docs as Markdown?What is the difference between /start.md, llms.txt, and llms-full.txt?Can API Reference pages be fetched as Markdown?
Inspect evidence visually
Playground & Replay